基于快速非支配排序遗传算法的共享电单车归还策略

Return Strategy of Shared E-bikes based on Fast Nondominated Sorting Genetic Algorithm

为满足当前共享电单车随取随停的需求,解决其缺乏规范管理而导致的乱停乱放现象及其所呈现出的“多、散、乱”的状态与区域性供给不平衡问题,构建了基于多目标规划模型的平衡状态下的共享电单车归还模型。首先,应用快速非支配排序遗传算法(NSGA-Ⅱ)确定平衡状态下的归还点分配方案;然后,结合专家打分、COWA算子、博弈论组合赋权法和TOPSIS法,从帕累托最优解集中选出最佳方案;最后,通过对比普通归还点分配方案里的用户所需付出的步行代价、时间代价和共享电单车的区域供给性,来验证实验结果的有效性。

In order to meet the current need of the shared e-bikes that are parked on demand,solve the problem of disorderly parking caused by the lack of standardized management,as well as the problem of“multiple,scattered,and disorderly”state and regional supply imbalance,a return model of shared e-bikes under balanced state based on the multi-objective programming model was constructed.Moreover fast nondominated sorting genetic algorithm(NSGA-Ⅱ)was applied to determine the return address allocation scheme under the state of equilibrium.Combining expert scoring,COWA operator,game theory combination weighting method and TOPSIS method,the best scheme was selected from the Pareto optimal solution set.Finally,the effectiveness of the experimental results was verified by comparing the walking cost,time cost and the regional availability of shared e-bikes that users need to pay in the general return addresses distribution scheme.